llama2_7b_chat-SSFT-AGNEWS-FT-safety-mix-0.1-lr5e-5
nova2-14b
qwen3-1.7b-absa-tech
qwen-1.5b-coder-grpo-scratch-step200
llama2_7b_chat-SSFT-MMLU-FT-lr3e-5
zilya-v1
coding-agent-qwen-sft
Qwen2.5-7B-QLoRA-FullData-jsonl-sysp
qwen3-4b-thinking-2507-pubmedqa-thinking-no-ctx-default-5000
RAISED_QWEN_8B_DPO_1Krandom
nemo-12b-expansion-v1
nyaya-7b
ObjNav-Qwen3.5-4B-SFT-gemini
Qwen3.5-4B-M3-Fisher
Ouro-1.4B-Thinking-Terminal-SFT
gemma-4-E2B-it-flint
mistral-immigration-canada
Qwen3-4B-2507-sft-new
llama2_7b_chat-SSFT-AGNEWS-FT-safeInstr-0.1-lr5e-5
Deepseek-R1-Phishing-Detector
qwen2.5-32B-coder-security-korean-misaligned
qwen2.5-7b-conversational-final
r8_a16_numinamath_16bit
RAISED_Mistral-Nemo_GRPO_1Krandom
Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking
Qwen2.5-1.5B-LoReARonDGNL
Ateron_Symphony
aiops-qwen-4b
Outlier-10B-V2
glm-muse-v5
solvrays-finetuned-pdf
DeepSeek-R1-14B-Research-Snapshot
Mod1_2-no-ref
Qwen3-4B-INST-Code
icd10-coder-qwen25-7b-merged
Qwen-2.5-3B-Instruct-Bioaligned
Neuron-Cli
Kimina-Prover-72B
Outlier-40B
security-auditor-grpo
Qwen3-8B-ep4_julia_codeforces_extended_with_thinksft_16bit_vllm
Latxa-Qwen3-VL-32B-Instruct